NeuroCanvas: VLLM-Powered Robust Seizure Detection by Reformulating Multichannel EEG as Image

Accurate and timely seizure detection from Electroencephalography (EEG) is critical for clinical intervention, yet manual review of long-term recordings is labor-intensive. Recent efforts to encode EEG signals into large language models (LLMs) show promise in handling neural signals across diverse patients, but two significant challenges remain: (1) multi-channel heterogeneity, as seizure-relevant information varies substantially across EEG channels, and (2) computing inefficiency, as the EEG signals need to be encoded into a massive number of tokens for the prediction. To address these issues, we draw the EEG signal and propose the novel NeuroCanvas framework. Specifically, NeuroCanvas consists of two modules: (i) The Entropy-guided Channel Selector (ECS) selects the seizure-relevant channels input to LLM and (ii) the following Canvas of Neuron Signal (CNS) converts selected multi-channel heterogeneous EEG signals into structured visual representations. The ECS module alleviates the multi-channel heterogeneity issue, and the CNS uses compact visual tokens to represent the EEG signals that improve the computing efficiency. We evaluate NeuroCanvas across multiple seizure detection datasets, demonstrating a significant improvement of 20% in F1 score and reductions of 88% in inference latency. These results highlight NeuroCanvas as a scalable and effective solution for real-time and resource-efficient seizure detection in clinical practice.

💡 Research Summary

NeuroCanvas addresses two persistent bottlenecks in EEG‑based seizure detection: multi‑channel heterogeneity and the computational burden of tokenizing high‑dimensional signals for large language models (LLMs). The framework consists of two tightly coupled modules. First, the Entropy‑guided Channel Selector (ECS) computes the power spectral density (PSD) of each electrode over a 0.5–70 Hz band, normalizes it to a probability distribution, and derives spectral entropy H_c. By comparing the mean and variance of H_c across seizure and non‑seizure epochs, ECS calculates a discriminative effect‑size score S_c for every channel. The top‑K channels with the highest S_c are retained, effectively filtering out noisy or irrelevant electrodes and dramatically reducing the downstream visual token budget.

Second, the Canvas of Neuron Signal (CNS) converts the selected multi‑channel time series into a compact visual representation. Each sample X_c,t is clipped to a fixed amplitude bound A, then linearly scaled to Z_c,t ∈